Deepseek R1 Reasoner
This MCP server, developed by an unspecified author, provides a reasoning extension for locally running models using Deepseek r1. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers a tool for task planning and context-based reasoning. The implementation focuses on enabling AI agents to perform reasoning tasks without relying on remote models, using Ollama to run Deepseek r1 locally. It's particularly useful for applications requiring autonomous planning and decision-making capabilities, enabling use cases such as task decomposition, strategy formulation, and context-aware problem-solving while maintaining data privacy and reducing latency.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/michaelneale/deepseek-r1-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Deepseek R1 Reasoner from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.